Run on ~6GB VRAM (full/partial offload) for various use cases.
-
bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF
Text Generation • 4B • Updated • 18.6k • 85 -
lmstudio-community/gemma-3-4b-it-GGUF
Image-Text-to-Text • 4B • Updated • 386k • 27 -
bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF
Text Generation • 15B • Updated • 25k • 224 -
bartowski/open-r1_OlympicCoder-7B-GGUF
Text Generation • 8B • Updated • 2.47k • 10